Skip to content

AgentExec WebMCP & Base L2 Gateway

by Har50 · remote · no sign-in to list tools · v1.0.2 · published by GitHub user Har50

Monetization and execution gateway for autonomous AI agents on Base Mainnet

Deletes · 1Changes · 2
CompareRegistry entry

4 tools: 1 can delete or cancel things, 2 change things and 1 only read.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http gateway https://api.agentexec.dev/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warndry_run_simulation

    The server marks "dry_run_simulation" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "dry_run_simulation" says "run": a word for a change.

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Deletes or cancels 1Claude Code: deny
  • execute_onchain_intentSimulates and executes a gasless, sponsored Web3 transaction on Base L2 (e.g.No findings

    Why it is in this group

    • The name "execute_onchain_intent" says "execute": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Simulates and executes a gasless, sponsored Web3 transaction on Base L2 (e.g. token swaps, transfers). Runs Tenderly dry-run safety checks automatically before broadcasting. Requires an API key.

    Annotations the server declares

    • title: Execute on-chain intent
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
Changes things 2Claude Code: ask
  • dry_run_simulationSimulates a transaction on Tenderly without broadcasting.1 finding

    Why it is in this group

    • The name "dry_run_simulation" says "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "dry_run_simulation" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "dry_run_simulation" says "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Simulates a transaction on Tenderly without broadcasting. Returns predicted gas and balance changes. Works without an API key (rate-limited per client) unless the operator disables public simulation.

    Annotations the server declares

    • title: Dry-run simulation
    • readOnlyHint: true
    • openWorldHint: true
  • issue_session_keyIssue an ERC-7579 / ZeroDev-scoped session key (time limit, USDC spend cap, target whitelist).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Issue an ERC-7579 / ZeroDev-scoped session key (time limit, USDC spend cap, target whitelist). Requires an API key.

    Annotations the server declares

    • title: Issue session key
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
Only reads 1Claude Code: allow
  • get_smart_account_infoRetrieves the Agent Owner EOA address and counterfactual Safe Smart Wallet address on Base.No findings

    Why it is in this group

    • The name "get_smart_account_info" says "get": a word for reading.
    Description, as the server wrote it
    Retrieves the Agent Owner EOA address and counterfactual Safe Smart Wallet address on Base. Works without an API key.

    Annotations the server declares

    • title: Get smart account info
    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http gateway https://api.agentexec.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__gateway__get_smart_account_info"
    ],
    "ask": [
      "mcp__gateway__dry_run_simulation",
      "mcp__gateway__issue_session_key"
    ],
    "deny": [
      "mcp__gateway__execute_onchain_intent"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as gateway. Review it before you use it.